writing-beats

Writing, exploit——把原始素材组装成一段节拍旅程，在某个 beat 依赖一个术语之前先把它 grounded。

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/in-progress/writing-beats/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable instruction-only workflow with a clear sequenced procedure, user-approval checkpoints, and feedback loops for edits. Its only weakness is mild verbosity in the Grounding section, where the core idea is restated more than necessary.

Suggestions

Tighten the Grounding section by stating the prerequisite/introduced distinction once and trimming the re-derivations in the following paragraphs to reduce repeated explanation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining general concepts Claude already knows, but the Grounding section restates the same idea multiple times (e.g. the prerequisite/introduced distinction is explained then re-derived over several paragraphs) and could be tightened, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Despite being instruction-only with no code, the guidance is concrete and specific: a numbered 1–5 procedure, explicit per-write behaviors ("每次写入前都从磁盘重新读取文章文件"), and precise user-intent handling ("如果用户说 'rewrite that beat'... 就地编辑"), meeting the executable-guidance bar for instruction skills.	3 / 3
Workflow Clarity	The steps are clearly sequenced with an explicit loop (steps 3–5) and validation checkpoints: candidate beats are shown to the user before writing ("在写入文章文件之前先把这些 beats 展示给用户"), the file is re-read from disk each iteration, and the Writing rhythm section defines feedback loops for edits and rewrites.	3 / 3
Progressive Disclosure	No bundle files are needed and none are referenced; the body is well-organized into <what-to-do> and <supporting-info> with clearly headed subsections, which per the rubric's simple-skill note earns a 3 for well-organized sections without external references.	3 / 3
	Total	11 / 12 Passed

Description

35%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys a distinctive writing methodology but leans heavily on internal jargon and omits any explicit "Use when..." trigger clause, weakening trigger-term quality and completeness. It reads more like a tagline than a discovery description.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers users would say, e.g. 'Use when turning rough notes into a structured article or essay.'

Replace internal terms ('exploit', 'grounded', 'beat journey') with user-facing language, or pair each jargon term with a plain-language synonym so the description matches what a user would actually type.

Reframe in third person with concrete actions (e.g. 'Assembles raw material into a step-by-step article, grounding each new term before it is used') instead of the current tagline form.

Dimension	Reasoning	Score
Specificity	It names the domain ("Writing, exploit") and two conceptual actions ("把原始素材组装成一段节拍旅程", "在某个 beat 依赖一个术语之前先把它 grounded"), but these are abstract/jargon rather than a comprehensive list of concrete actions, matching the 'names domain and some actions' anchor.	2 / 3
Completeness	It states what the skill does but has no "Use when..." or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2 ('has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	The only natural user term is "Writing"; the rest ("exploit", "beat journey", "grounded a term") is internal vocabulary users would not naturally say, matching the 'no natural keywords; technical jargon' anchor like "Handles document object model manipulation".	1 / 3
Distinctiveness Conflict Risk	The methodology niche (beat-by-beat journey with grounding) is fairly specific and unlikely to overlap with most skills, but the weak trigger guidance and generic lead term "Writing" keep it from a clear, distinct-trigger score of 3.	2 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vinvcn/mattpocock-skills-zh-CN
Path: skills/in-progress/writing-beats/SKILL.md
Commit: f2b2464

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.